@theo I would’ve LOVED having latex support for the last few months of my thesis on t3 code but I just ended up using the html render instead🫠 even if it’s not practical
@theo@jullerino what do we think about a "Delegated" section for the sidebar? Whenever we answer it disappears and only appears back when it's done. That way the "inbox" is always encouraged to be empty
This felt so weird initially but I'm obsessed with it now. I have 18 threads working here and it doesn't feel claustrophobic anymore.
Things appear when they need your attention, and disappear when they don't.
I've always been curious about what's the longest session people ever had running, here's my small contribution
Also shoutout to @t3dotcodes being able to handle such long threads and having access to the machine everywhere is such a game changer
Just FYI. If you are switching models in a session all the time - you are doing it wrong.
Every time you switch, your entire prompt cache is invalidated on the new model you switch to, and you have to repay the full input tokens price for all of it.
Stop doing this unless those models are free.
This is not a hermes thing - this is a fundamentals of inference thing.
@theo@jullerino ALSO whenever threads get settled/auto-settled, wouldn't it be good for t3code to have git status since last opened not updated one constantly? Similar to how codex does it?
@theo@jullerino what do we think about a "Delegated" section for the sidebar? Whenever we answer it disappears and only appears back when it's done. That way the "inbox" is always encouraged to be empty